Model comparison
Gemini 2.0 Flash (Feb 2025) vs Gemma 3 27B
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 30.8 on the Noometry Index.
Last verified . 37 shared benchmarks.
GoogleSummary
- They share 37 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 8 categories and Gemma 3 27B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 25.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 22.5% for Gemma 3 27B.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B | |
|---|---|---|
| Provider | ||
| Noometry Index | 35.1 | 30.8 |
| Released | 2024-12-06 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 54 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Gemma 3 27B: 22.5 (#334)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| Aider Polyglot | 38.2% | 4.9% |
| LiveBench Coding | 63.4% | 39.9% |
| LMArena Coding | 1350 | 1322 |
| SWE-bench Verified (bash only) | 13.5% | — |
| SciCode | — | 21.2% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Gemma 3 27B: 25.1 (#110)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
| TheAgentCompany | 11.4% | — |
Reasoning Gemma 3 27B leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Gemma 3 27B: 16.7 (#301)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 40.4% |
| LiveBench Reasoning | 78.2% | 43.8% |
| LMArena Hard Prompts | 1346 | 1340 |
| DTBench | 63.2% | 52.5% |
| LiveBench Data Analysis | 69.4% | 51.5% |
| Epoch Capabilities Index | 135.36 | 130.04 |
| LiveBench | 66.9% | 50% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 1.1% | — |
| LMCA | — | 12.3% |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Gemma 3 27B: 25.9 (#265)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 22.5% |
| LiveBench Math | 75.8% | 55.4% |
| LMArena Math | 1352 | 1312 |
| MATH Level 5 | 82.2% | 74% |
| Omni-MATH | 45.9% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Gemma 3 27B: 25.5 (#261)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 64.1% | 47.7% |
| Confabulations | 12.4% | 40.3% |
| LMArena Expert | 1339 | 1304 |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Gemma 3 27B: 32.6 (#100)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 1158 | 1164 |
| GeoBench | 77% | 52% |
Multilingual Too close to call
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Gemma 3 27B: 46.9 (#155)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1342 | 1334 |
| LMArena Chinese | 1373 | 1346 |
| LMArena French | 1391 | 1368 |
| LMArena German | 1353 | 1362 |
| LMArena Japanese | 1294 | 1287 |
| LMArena Korean | 1313 | 1308 |
| LMArena Russian | 1351 | 1349 |
| LMArena Spanish | 1363 | 1349 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Gemma 3 27B: 70.6 (#160)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 74.9% |
| LMArena Instruction Following | 1336 | 1321 |
| IFEval | 84.1% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Gemma 3 27B: 27.6 (#293)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| Fiction.LiveBench | 61.1% | 33.3% |
| LMArena Longer Query | 1344 | 1333 |
Writing & Preference Gemma 3 27B leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Gemma 3 27B: 52.5 (#168)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1354 | 1358 |
| LMArena Creative Writing | 1340 | 1346 |
| Short-Story Creative Writing | 73.8% | 79.9% |
| EQ-Bench Creative Writing | 1128 | 1266 |
| LMArena Multi-Turn | 1350 | 1345 |
| LiveBench Language | 51.3% | 34.6% |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Gemma 3 27B?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 30.8 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Gemma 3 27B better for coding?
Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.4 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Gemma 3 27B share?
37 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Gemma 3 27B has 43.